Study on predictive about manufacturing precision of the bore of bearing inter rings based on neural network theory

Based on specific features of the neural network, this paper is concerned with its application to prediction of nonlinear time sequence. A mathematical model of the dynamic distribution of dimension error in bore of bearing internal grinding process is established by means of the neural network theory. And the calculated precision between gray system model GM(1,1) and BPNN model are compared. The result shows that the calculated precision is higher for BPNN model then that for the gray system model.